AI method for generating proteins for a fast drug development
2021
Chalmers University of Technology, Gothenburg, Sweden
ProteinGAN is artificial intelligence (AI) software that can ‘learn’ natural protein sequence diversity and enables the generation of functional protein sequences. It learns the evolutionary relationships of protein sequences directly from the complex multidimensional amino-acid sequence space and creates new, highly diverse sequence variants with natural-like physical properties. Unlike the very slow classical protein engineering, ProteinGAN allows researchers to go from computer design to working protein in just a few weeks, driving down development costs. The new AI-based approach is important for developing efficient industrial enzymes and new protein-based therapies, such as antibodies and vaccines.
Expanding functional protein sequence spaces using generative adversarial networks
Aleksej Zelezniak
Added on: 05-11-2021
[1] https://www.nature.com/articles/s42256-021-00310-5[2] https://www.bionity.com/en/news/1170469/unique-ai-method-for-generating-proteins-will-speed-up-drug-development.html
